---
title: "Observe, optimize and protect your hosted agents in Microsoft Foundry"
category: "talks"
date: "2026-06-29"
time: "2:20pm-3:35pm"
track: "Track M"
room: "Track M"
speakers: ["Pamela Fox"]
sourceLabels: ["Official conference schedule", "Public YouTube metadata"]
scheduleTrack: "Track M"
scheduleRoom: "Track M"
scheduleLabels: ["Track M", "Track M", "sponsor", "confirmed"]
---
# Observe, optimize and protect your hosted agents in Microsoft Foundry

## Conference Context
- Date/time: 2026-06-29 · 2:20pm-3:35pm
- Track/room: Track M · Track M
- Speaker(s): Pamela Fox
- Session type/status: sponsor · confirmed

- Track: Track M
- Room: Track M
- Session type: sponsor
- Status: confirmed

## Session Description
Modern agents fail in ways traditional monitoring can’t catch. In this hands-on lab, learn how Microsoft Foundry Observability helps you move from prototype → production with context-specific evaluation suites (auto-generated evaluators + test datasets) wired into developer workflows via skills/MCP tooling for hosted agents. Then scale quality with continuous evaluation, trace-linked analysis, and adaptive red teaming—and walk away with a sandbox to explore additional features on your own.

## Media Evidence
[Running AI Application in Minutes w/ AI Templates: Gabriela de Queiroz, Pamela Fox, Harald Kirschner](https://www.youtube.com/watch?v=1t-9-s1brcg) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

- Source video: `youtube-1t-9-s1brcg`
- Slide deck: [[youtube-1t-9-s1brcg-dense-slides|Dense Slides: Running AI Application in Minutes w/ AI Templates: Gabriela de Queiroz, Pamela Fox, Harald Kirschner]] — 50 visible slide image(s); 50 HTML recreation(s).
![[assets/dense-slides/1t-9-s1brcg/slide-001.jpg]]
![[assets/dense-slides/1t-9-s1brcg/slide-002.jpg]]
![[assets/dense-slides/1t-9-s1brcg/slide-003.jpg]]
- Additional slide evidence: [[youtube-1t-9-s1brcg-slides|Slides: Running AI Application in Minutes w/ AI Templates: Gabriela de Queiroz, Pamela Fox, Harald Kirschner]], [[youtube-1t-9-s1brcg-reconstructed-slides|Reconstructed Slides: Running AI Application in Minutes w/ AI Templates: Gabriela de Queiroz, Pamela Fox, Harald Kirschner]]
- Slide-derived themes for `youtube-1t-9-s1brcg`: azure, proxy, templates, microsoft, startups, founders, startup, faster.

## Evidence Graph
This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

### Media Signals
- `youtube-1t-9-s1brcg` — 6 slide-derived text signals
- Slide-derived themes for `youtube-1t-9-s1brcg`: azure, proxy, templates, microsoft, startups, founders, startup, faster.
- Evidence links for `youtube-1t-9-s1brcg`: [[youtube-1t-9-s1brcg]], [[youtube-1t-9-s1brcg-slides]], [[youtube-1t-9-s1brcg-dense-slides]], [[youtube-1t-9-s1brcg-reconstructed-slides]]

### Agent Reading Notes
Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

## Transcript Status
Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.

## People
- [[pamela-fox]]

## Supporting Slides
- [[youtube-1t-9-s1brcg-slides]] — extracted from the related public AI Engineer video.

## Slide Evidence
- Slide-only cropped deck: [[youtube-1t-9-s1brcg-dense-slides]] (50 viable slide images).
- Related slide/OCR pages:
- [[youtube-1t-9-s1brcg-dense-slides]]
- [[youtube-1t-9-s1brcg-reconstructed-slides]]
- [[youtube-1t-9-s1brcg-slides]]
- Slide-derived terms: `azure`, `microsoft`, `github`, `startups`, `account`, `workshop`, `boars`, `founders`, `instructions`, `open`, `mode`, `gene`, `they`, `engineer`, `signin`, `login`, `pass`, `will`

## Synthesis
### Synthesized Breakdown
# Observe, optimize and protect your hosted agents in Microsoft Foundry ## Conference Context - Date/time: 2026-06-29 · 2:20pm-3:35pm - Track/room: Track M · Track M - Speaker(s): Pamela Fox - Session type/status: sponsor · confirmed - Track: Track M - Room: Track M - Session type: sponsor - Status: confirmed ## Session Description Modern agents fail in ways traditional monitoring can’t catch. In this hands-on lab, learn how Microsoft Foundry Observability helps you move from prototype → production with context-specific evaluation suites (auto-generated evaluators + test datasets) wired into developer workflows via skills/MCP tooling for hosted agents. Then scale quality with continuous evaluation, trace-linked analysis, and adaptive red teaming—and walk away with a sandbox to explore additional features on your own. ## Media Evidence [Running AI Application in Minutes w/ AI Templates: Gabriela de Queiroz, Pamela Fox, Harald Kirschner](https://www.youtube.com/watch?v=1t-9-s1brcg) (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

### Speaker And Company Context
- [[pamela-fox|Pamela Fox]] — Principal Cloud Advocate at [[microsoft|Microsoft]].

### Topics Covered
- [[ai-sandboxes]]
- [[coding-agents]]
- [[mcp]]

### Derived Links And Source Material
- [[youtube-1t-9-s1brcg]] — related YouTube source page.
- [[youtube-1t-9-s1brcg-slides]] — slide evidence.
- [[youtube-1t-9-s1brcg-reconstructed-slides]] — slide evidence.
- [[youtube-1t-9-s1brcg-dense-slides]] — slide evidence.

### Novel Concepts / Clever Methods
- No highlighted novel concept has been detected yet.

### Evidence Boundary
This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.